Solved – global max pooling layer and what is its advantage over maxpooling layer

Question

Can somebody explain what is a global max pooling layer and why and when do we use it for training a neural network. Do they have any advantage over ordinary max pooling layer?

Answer 1

Global max pooling = ordinary max pooling layer with pool size equals to the size of the input (minus filter size + 1, to be precise). You can see that MaxPooling1D takes a pool_length argument, whereas GlobalMaxPooling1D does not.

For example, if the input of the max pooling layer is $0,1,2,2,5,1,2$, global max pooling outputs $5$, whereas ordinary max pooling layer with pool size equals to 3 outputs $2,2,5,5,5$ (assuming stride=1).

This can be seen in the code:

class GlobalMaxPooling1D(_GlobalPooling1D):
    """Global max pooling operation for temporal data.
    # Input shape
        3D tensor with shape: `(samples, steps, features)`.
    # Output shape
        2D tensor with shape: `(samples, features)`.
    """

    def call(self, x, mask=None):
        return K.max(x, axis=1)

In some domains, such as natural language processing, it is common to use global max pooling. In some other domains, such as computer vision, it is common to use a max pooling that isn't global.